 saleml
|
b1f0799f59
Merge branch 'master' into newstep
|
пре 2 година |
 Rodrigo Perez-Vicente
|
bd7ed2c3c3
mission space
|
пре 2 година |
|
saleml
|
71d38fa37d
Merge branch 'master' into newstep
|
пре 2 година |
|
Rodrigo Perez-Vicente
|
6268ef0cf0
Register environments with entrypoint in setup.py
|
пре 2 година |
|
saleml
|
5c241a8a15
use new_step API, and solve some pylance errors
|
пре 2 година |
|
Rodrigo Perez-Vicente
|
8c879a1fa2
fix rebase pre-commit
|
пре 2 година |
|
Rodrigo Perez-Vicente
|
3aab399ab1
Add pyright to pre-commit
|
пре 2 година |
 StringTheory
|
5e40e4c117
Run pre-commit
|
пре 2 година |
|
StringTheory
|
e30599f258
Merge branch 'master' into remove-param-envs
|
пре 2 година |
|
StringTheory
|
925419ffbf
Rerun pre-commit
|
пре 2 година |
|
StringTheory
|
d9fa55fd69
Merge branch 'master' into pre-commit
|
пре 2 година |
|
StringTheory
|
d53edeb5a2
Initial commit
|
пре 2 година |
|
StringTheory
|
c345e9027f
Initial commit for adding pre-commit
|
пре 2 година |
|
saleml
|
ce22f87a27
add **kwargs to __init__ functions of all classes inhertting from MiniGridEnv, in order to be able to use gym.make the right way
|
пре 2 година |
 Maxime Chevalier-Boisvert
|
c99822121e
Added reward penalty based on number of time steps taken
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
636226f90e
Renamed wait action to done
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
146fd10741
Made reward_range the same for all environments, rewards are in [0, 1]
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
852476db7c
Finished renaming MiniGrid methods for PEP8 conformance
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
bfd0f76513
Faster visibility algorithm. Method renamings.
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
ec9e19efe7
Renamed fields to match PEP8 convention
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
3c52268b00
Progress on RoomGrid-v0 env
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
340c03a446
Cleaned up and simplified _genGrid functions
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
c4049b13ed
Added Playground-v0 environment for experiments
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
2b1d180dda
Corrected reward ranges for environments
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
25fe4664fa
Modified environments so they all produce observations in a dict
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
114caa944a
Fixes based on changes in OpenAI Gym 0.9.6
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
c46ade2f4f
Fixed bug in fetch environment
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
723359da33
Removed waitEnds flag
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
73e6d3d2f1
Made adjustments to GoToObject based on GoToDoor env
|
пре 7 година |
|
Maxime Chevalier-Boisvert
|
3d0c94f876
Removed "advice" from observations. Randomized GoToDoor room size.
|
пре 7 година |
